From d8641f3692a741f0411b179efcdd748ef0376f7e Mon Sep 17 00:00:00 2001 From: Ervin Teng Date: Thu, 20 Aug 2020 12:06:05 -0700 Subject: [PATCH] Update changelog --- com.unity.ml-agents/CHANGELOG.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/com.unity.ml-agents/CHANGELOG.md b/com.unity.ml-agents/CHANGELOG.md index 44f4b202ea..d55cefbac5 100755 --- a/com.unity.ml-agents/CHANGELOG.md +++ b/com.unity.ml-agents/CHANGELOG.md @@ -29,6 +29,10 @@ and this project adheres to - The interaction between EnvManager and TrainerController was changed; EnvManager.advance() was split into to stages, and TrainerController now uses the results from the first stage to handle new behavior names. This change speeds up Python training by approximately 5-10%. (#4259) +- Experimental PyTorch support has been added. Use `--torch` when running `mlagents-learn`, or add +`framework: pytorch` to your trainer configuration (under the behavior name) to enable it. +Note that PyTorch 1.6.0 or greater should be installed to use this feature; see +[the PyTorch website](https://pytorch.org/) for installation instructions. (#4335) ### Minor Changes #### com.unity.ml-agents (C#)